File size: 6,031 Bytes
7a54239
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
{
  "best_metric": 1.2656669616699219,
  "best_model_checkpoint": "buscuit_wrappers_image_detection/checkpoint-3160",
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 3160,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.46677215189873417,
      "eval_loss": 4.141796112060547,
      "eval_runtime": 45.8267,
      "eval_samples_per_second": 27.582,
      "eval_steps_per_second": 3.448,
      "step": 158
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9137658227848101,
      "eval_loss": 3.748347520828247,
      "eval_runtime": 45.8167,
      "eval_samples_per_second": 27.588,
      "eval_steps_per_second": 3.449,
      "step": 316
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9707278481012658,
      "eval_loss": 3.340620994567871,
      "eval_runtime": 45.4201,
      "eval_samples_per_second": 27.829,
      "eval_steps_per_second": 3.479,
      "step": 474
    },
    {
      "epoch": 3.16,
      "learning_rate": 8.553054662379421e-06,
      "loss": 3.852,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9825949367088608,
      "eval_loss": 2.9873366355895996,
      "eval_runtime": 45.937,
      "eval_samples_per_second": 27.516,
      "eval_steps_per_second": 3.439,
      "step": 632
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.990506329113924,
      "eval_loss": 2.687716007232666,
      "eval_runtime": 46.1528,
      "eval_samples_per_second": 27.387,
      "eval_steps_per_second": 3.423,
      "step": 790
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.992879746835443,
      "eval_loss": 2.4411532878875732,
      "eval_runtime": 45.5826,
      "eval_samples_per_second": 27.73,
      "eval_steps_per_second": 3.466,
      "step": 948
    },
    {
      "epoch": 6.33,
      "learning_rate": 6.945337620578779e-06,
      "loss": 2.6909,
      "step": 1000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9944620253164557,
      "eval_loss": 2.232517957687378,
      "eval_runtime": 45.3522,
      "eval_samples_per_second": 27.871,
      "eval_steps_per_second": 3.484,
      "step": 1106
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9944620253164557,
      "eval_loss": 2.0533387660980225,
      "eval_runtime": 45.488,
      "eval_samples_per_second": 27.788,
      "eval_steps_per_second": 3.473,
      "step": 1264
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.997626582278481,
      "eval_loss": 1.903907060623169,
      "eval_runtime": 45.3377,
      "eval_samples_per_second": 27.88,
      "eval_steps_per_second": 3.485,
      "step": 1422
    },
    {
      "epoch": 9.49,
      "learning_rate": 5.3376205787781355e-06,
      "loss": 1.9834,
      "step": 1500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9992088607594937,
      "eval_loss": 1.7741676568984985,
      "eval_runtime": 45.2098,
      "eval_samples_per_second": 27.959,
      "eval_steps_per_second": 3.495,
      "step": 1580
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.9992088607594937,
      "eval_loss": 1.665787696838379,
      "eval_runtime": 45.5267,
      "eval_samples_per_second": 27.764,
      "eval_steps_per_second": 3.47,
      "step": 1738
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.9992088607594937,
      "eval_loss": 1.5742113590240479,
      "eval_runtime": 45.4975,
      "eval_samples_per_second": 27.782,
      "eval_steps_per_second": 3.473,
      "step": 1896
    },
    {
      "epoch": 12.66,
      "learning_rate": 3.7299035369774923e-06,
      "loss": 1.5675,
      "step": 2000
    },
    {
      "epoch": 13.0,
      "eval_accuracy": 0.9992088607594937,
      "eval_loss": 1.496795892715454,
      "eval_runtime": 45.3684,
      "eval_samples_per_second": 27.861,
      "eval_steps_per_second": 3.483,
      "step": 2054
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.9992088607594937,
      "eval_loss": 1.4344640970230103,
      "eval_runtime": 45.2152,
      "eval_samples_per_second": 27.955,
      "eval_steps_per_second": 3.494,
      "step": 2212
    },
    {
      "epoch": 15.0,
      "eval_accuracy": 0.9992088607594937,
      "eval_loss": 1.3806020021438599,
      "eval_runtime": 45.4167,
      "eval_samples_per_second": 27.831,
      "eval_steps_per_second": 3.479,
      "step": 2370
    },
    {
      "epoch": 15.82,
      "learning_rate": 2.122186495176849e-06,
      "loss": 1.3295,
      "step": 2500
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.9992088607594937,
      "eval_loss": 1.3391495943069458,
      "eval_runtime": 45.5303,
      "eval_samples_per_second": 27.762,
      "eval_steps_per_second": 3.47,
      "step": 2528
    },
    {
      "epoch": 17.0,
      "eval_accuracy": 0.9992088607594937,
      "eval_loss": 1.306061029434204,
      "eval_runtime": 45.6177,
      "eval_samples_per_second": 27.709,
      "eval_steps_per_second": 3.464,
      "step": 2686
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 1.0,
      "eval_loss": 1.2838025093078613,
      "eval_runtime": 45.7211,
      "eval_samples_per_second": 27.646,
      "eval_steps_per_second": 3.456,
      "step": 2844
    },
    {
      "epoch": 18.99,
      "learning_rate": 5.144694533762058e-07,
      "loss": 1.2076,
      "step": 3000
    },
    {
      "epoch": 19.0,
      "eval_accuracy": 1.0,
      "eval_loss": 1.2703361511230469,
      "eval_runtime": 45.5384,
      "eval_samples_per_second": 27.757,
      "eval_steps_per_second": 3.47,
      "step": 3002
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 1.0,
      "eval_loss": 1.2656669616699219,
      "eval_runtime": 45.3563,
      "eval_samples_per_second": 27.868,
      "eval_steps_per_second": 3.484,
      "step": 3160
    }
  ],
  "logging_steps": 500,
  "max_steps": 3160,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 7.838436403987661e+18,
  "trial_name": null,
  "trial_params": null
}